Pay per use · No subscriptions
Honest, per-token pricing.
Top up once. Spend at per-model token rates. Same prices for everyone, from your first request to your millionth. No monthly fee. No lock-in. Credits never expire.
No card required. Try every model end-to-end before you spend a cent. Top up to unlock 600 RPM and 1M tokens/min.
Per-token pricing
All prices in USD per million tokens. Cached prompts and embeddings are billed separately at lower rates.
| Model | Family | Input / 1M | Output / 1M | Context (tokens) |
|---|---|---|---|---|
| translategemma-4b | gemma | $0.05 | $0.2 | 131,072 |
| qwen3 | qwen | $0.1 | $0.3 | 32,768 |
| deepseek-ocrFeatured | deepseek | $0.2 | $0.8 | 8,192 |
| llama3.1Featured | llama | $0.2 | $0.4 | 128,000 |
| gemma3Featured | gemma | $0.3 | $0.6 | 8,192 |
| deepseek-r1 | deepseek | $0.3 | $0.9 | 32,768 |
| gpt-oss-120bFeatured | gpt-oss | $0.4 | $1.2 | 131,072 |
| qwen3-coderFeatured | deepseek | $0.6 | $1.8 | 32,768 |
| nomic-embedEmbedding | embedding | $0.05 | — | 8,192 |
Prices are billed per token of completed request, rounded to the nearest millionth of a dollar. We do not charge for failed requests.
Credits never expire
Top up once, use over months. We don't burn your balance for inactivity.
Hard spend caps
Per-key daily and monthly caps stop runaway agents before they drain your balance.
Same price for everyone
No volume tiers, no enterprise tax. Your first request costs the same as your millionth.
Start with $1 of free credit.
No card. No subscription. Just an API key and 8 self-hosted open models.